Models

exp_tas_frequency_penalty_0_5_traces

detail-14b-0.839086

Qwen3-8B-ot_step70

Qwen3-8B-tacq-3bit-calibration-English-128samples

Qwen3-8B-slimllm-3bit-calibration-Indonesian-128samples

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

OpenGemini-Flash-RLVR

Qwen3-1.7B-Base_csum_6_10_rel_1e-3_1p0_0p0_1p0_grpo_1_rule

Qwen3-8B_exp_tas_summarize_threshold_4096_traces_save-strategy_steps

cso-q3-14b-8x8-swe_smith-multilevel_f05_minimum-terminal-250

Affine-193-5CtmVuY8eCeumgbEps55Bknw9vjuLqHsiQH7dcc3kaXXUb7r

affine-YB125-5FUNpXswwBPbYZfuJxEsgSdEx4bonLteeEzmBXapRxrPg4Kf

Qwen3-1.7B-Base_csum_6_10_final_1p0_0p0_1p0_grpo_42_rule

vd-8-step58

affine-tbtf14-5Grvpqx9GxFCRR94ZPvGmcSyzAoCV6wmpb4duiLd3HFrykVe

affine-00-5E9ffBCnChMfm8RkghPgDgzQdg7XHwbdJouk7cd7fH34SwQr

Qwen3-14B_merged

tbench-qwen-sft-multitask-nat-v8

tbench-qwen-sft-fix-git-overfit-v7-nat-fixed

affine-v4-5FsZP1ipNDE6Esg9rf8AnepyXQFC8xRKQFWPRRFr15p9covj

qwen3-14b-rl

KomdigiUB-8B-Instruct-DTP

SearchAgent-8B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_7.0_Qwen3-32B

VLM_stage_2_iter_0004000

appworld-agent-8B-no-think-new-agent-multilock-dev-0122-global-step-700

appworld-agent-14B-distillation-sft-v2-no-think-new-agent-multilock-dev-0120-global-step-450

exp_tas_top_k_64_traces

cso-q3-14b-32x4-swe_smith-multilevel_f1_minimum-custom_tool-400

Qwen3-8B-Tiny-Hanabi-SFT

exp_tas_max_tokens_1024_traces

exp_tas_summarize_threshold_2048_traces

model_of_encoded-reasoning_2

pytest-generator-v4

FlowSteer-8b

GRPO_final_submission

broken-model-fixed

tsundere-1-mxfp4

Affine-5Ey2gdmMeDJ1Z3XGzDKfpYq18jEZ83gqx7pz78pLsGrY6KL5

FIRE-RM

Sindhi-Qwen3-14B-Full

qwenb_2.json_train_grpo_v1_train_code